WO2024013577A1 - An intelligent farm task management system - Google Patents

An intelligent farm task management system Download PDF

Info

Publication number
WO2024013577A1
WO2024013577A1 PCT/IB2023/054365 IB2023054365W WO2024013577A1 WO 2024013577 A1 WO2024013577 A1 WO 2024013577A1 IB 2023054365 W IB2023054365 W IB 2023054365W WO 2024013577 A1 WO2024013577 A1 WO 2024013577A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
farm
layer
task management
management system
Prior art date
Application number
PCT/IB2023/054365
Other languages
French (fr)
Inventor
Faras MORADKHANI
Taher PARYAB
MohammadAli FARAHBAKHSH
MohammadAli MOAZZEN
Original Assignee
Moradkhani Faras
Paryab Taher
Farahbakhsh Mohammadali
Moazzen Mohammadali
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Moradkhani Faras, Paryab Taher, Farahbakhsh Mohammadali, Moazzen Mohammadali filed Critical Moradkhani Faras
Priority to PCT/IB2023/054365 priority Critical patent/WO2024013577A1/en
Publication of WO2024013577A1 publication Critical patent/WO2024013577A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/105—Human resources

Definitions

  • the present invention relates to an agricultural field management system, to an agricultural field management method, and a management system in an agricultural field such as a farm, an agricultural field, and the like.
  • Drones and Satellites Drones equipped with cameras and sensors provide real-time footage of crop growth and yield estimates, which can be helpful for farmers in optimizing their operations. Additionally, satellites are also used to observe crop growth and healthy soil from space, giving farmers access to comprehensive data.
  • Farms are leveraging Al and machine learning technologies to get improved insights into crop disease recognition, prediction of crop yields, and to make recommendations on how to optimize production.
  • Chinese Patent Publication No. CN112036717 discloses a smart agriculture product traceability management system based on the Internet of Things, which falls under the agricultural Internet of Things technology domain.
  • the system encompasses various subsystems such as digital farm management, traceability code generation and printing, Internet of Things, agricultural remote sensing application, 5G-powered VR video monitoring, 5G-based hyperspectral video monitoring, cold chain standardization information, and e-commerce inventory and delivery integration.
  • Korean Patent Publication No. KR1020100011363 discloses a system and method for customized feeding in a farm using a remote management unit have been developed to provide the appropriate mixing ratio of feed for different livestock.
  • the system comprises a farm data-acquiring unit that collects environmental and growth-related information along with weight and feed data. Farm data is transmitted and received via a farm data transceiver.
  • the remote management unit receives the data via a network and manages the farm environment to ensure optimal growth conditions.
  • the unit analyzes the amount of feed consumed by the livestock in response to changes in the environment and weight gain and provides customized feeding based on the raw materials and nutrient content of the feed, tailored to the growth stage of the livestock.
  • the proposed model is an intelligent farm task management system that utilizes information and communication technologies to collect and analyze realtime data for each farm.
  • the system consists of five layers, including the data collection layer, web service layer, cloud storage layer, application layer, and user layer.
  • Smart farm management systems can collect environmental data from large- scale farms in a wide range and upload them in real-time, and issue task management commands in real-time. Also, by using intelligent decision-making algorithms without human intervention, fully automated and flexible management of agricultural production can significantly reduce labor, improve management efficiency and technical level, prevent human intrusion as much as possible, improve the quality and productivity of agricultural products, and achieve the best results based on variable farm conditions. Moreover, the dynamic task generator helps workers minimize their idle time in case of any changes in the system. This improves their morale and reduces stress, errors, and enhances their confidence.
  • Fig.1 illustrates a block diagram of the invention showing the overall configuration of a smart farm task management system.
  • Fig.2A and B show the operation of the software and how to determine the map of agricultural land and labor force and new machines and other activities.
  • Fig.3 shows the connection between input information and the types of information (records) output in the smart.
  • Fig.4 shows the block diagram of the user environment and the system environment and the incorporation of the ANFIS, ASCE, and FAO methods for more accurate predictions.
  • Fig.5 shows an example of tasks performed records and assigned to farmers or employees created by the intelligent system.
  • the system has a five-layer distributed architecture divided into a data collection layer, a web service layer, a cloud storage layer, an application layer, and a user layer.
  • This layer is responsible for collecting data from various sources such as sensors, loT devices, and databases.
  • the collected data can include information about temperature, humidity, soil moisture, crop growth, and weather conditions.
  • the data is transmitted to the cloud storage layer for further processing and analysis.
  • the database includes the data inputted by the farm manager.
  • the collected information includes data such as land use, farm map, employees, machinery, and other equipment.
  • This module also allows users to add and receive information from other users and provides permissions, daily task management forms, and daily reports to the user.
  • the farm production activity information (such as planting, pruning, irrigation, pesticide application, harvesting, and cleaning), labor information, and production process information are manually entered by the manager, while environmental information is automatically uploaded through web services.
  • Web Service Layer This layer provides the interface between the application layer and the cloud storage layer. It consists of web services that allow the application layer to retrieve and manipulate data stored in the cloud storage layer. The web services also enable communication between the different components of the system.
  • Cloud Storage Layer This layer is responsible for storing the collected data and processed information. It provides a scalable and secure platform for data storage and management.
  • the cloud storage layer can also be used to perform data analysis and generate insights that can be used by the application layer to make decisions and take actions.
  • the cloud storage layer includes multidimensional data resources (e.g., technical regulations data, primary data, and production archive data).
  • the application layer of the system is responsible for processing and analyzing the data collected from the data collection layer. It performs various tasks such as data filtering, sorting, and aggregation to derive meaningful insights from the data.
  • the layer also includes various algorithms and models that are used for predictive analytics and decision-making.
  • the application layer interacts with the cloud storage layer to store the processed data and with the user layer to present insights and analytics in a user-friendly manner.
  • the application layer consists of main functional modules that together support the efficient management of the farm, including the following modules:
  • a communication module for transmitting and receiving data to and from the cloud system.
  • a real-time monitoring module for the central server which receives environmental information such as temperature or humidity from the system and analyzes information from each farm, performing real-time monitoring based on the results of the analysis.
  • An information analysis module the module analyzes environmental and farm data and provides the results of the analysis at specified intervals. This module also publishes reports on performance, workforce, and resources (weekly, monthly, and yearly).
  • a wireless control module for facilities and machinery which is responsible for remote control of farm facilities and equipment.
  • a dynamic task generator module using real-time monitoring module data automatically determines and changes tasks using conditional logic in response to whether a criterion is above a threshold. For example, if the soil moisture system exceeds the threshold limit, it can send an automatic notification to the farmer to water the plants.
  • the user layer of the system is the front-end interface that allows users to interact with the system. It includes various components such as a web or mobile application, dashboards, and reports.
  • the user layer provides users with realtime access to the data and analytics generated by the system. It allows users to visualize the data, generate reports, and make informed decisions based on the insights provided by the system.
  • the user layer also includes various features such as alerts, notifications, and collaboration tools to facilitate communication and collaboration among users.
  • FIG. 1 A block diagram shows the overall configuration of a smart farm task management system according to the preferred embodiment of the present invention.
  • smart farm task management includes the following stages:
  • Data collection This system collects data from various sources such as sensors, weather forecasting applications, and pest detection systems.
  • Task generation Based on the analyzed data, the system generates a list of tasks that need to be performed on the farm.
  • the system uses conditional logic to dynamically change tasks based on farm conditions. For example, if it rains, irrigation tasks may be delayed and disease control tasks may take priority.
  • Task execution Generated tasks are assigned to the relevant personnel and executed, and the system updates the status.
  • FIG.2 a general flow of a farm task management system with conditional logic is illustrated, and it can be customized based on specific needs.
  • FIG.2A,B the flow chart shows how to determine the map of agricultural land and labor force and new machines and other activities. Activities are in series, meaning that one activity takes precedence over another. For example, in a land, the first activity is plowing, then irrigation. Therefore, when these activities are given to employees as a task, the same rules apply: that is, someone who has an irrigation task cannot start working until someone who has a plowing task finished his work.
  • the proposed innovation is a state-of-the-art neural network system that aims to revolutionize agriculture management by predicting soil moisture content with high accuracy.
  • This advanced system uses a combination of artificial neural networks, fuzzy logic, and optimization algorithms to gather, preprocess, and analyze data from various sources such as weather stations, soil sensors, and agricultural land location.
  • the system By accurately predicting soil moisture content, the system provides farmers with valuable insights into their operations, enabling them to make informed decisions about irrigation and other agricultural practices. This can lead to optimized operations, increased crop yields, and reduced water waste. Moreover, the system can adapt to changing conditions in real time, ensuring accurate predictions even in dynamic environments.
  • the system employs a powerful neural network architecture, consisting of input, hidden, and output layers, to accurately model the complex relationships between the input variables and the output variables (for example soil moisture).
  • the BFGS optimization algorithm is used to iteratively update the weights of the neural network, resulting in a more accurate prediction model.
  • the system also incorporates the ANFIS, ASCE, and FAO methods for more accurate predictions.
  • the ANFIS method provides linguistic interpretability, while the ASCE method considers various factors such as precipitation, temperature, humidity, and wind speed.
  • the FAO method takes into account factors such as climate, soil type, and crop characteristics, resulting in a more comprehensive and accurate prediction model as shown in Fig. 4.
  • the system also employs data preprocessing and feature selection techniques to ensure that only the most relevant data is used for prediction.
  • the data is aggregated from various sources such as sensor data, farm location, worker abilities, UAV camera images, and other unpredictable items.
  • the proposed innovation provides an advanced and comprehensive solution for predicting soil moisture content in agricultural settings, leveraging advanced technologies and methodologies to help farmers make informed decisions and achieve better outcomes.
  • the flowchart shows one of the tasks of the farm, irrigation, where the system can optimize water and soil usage by providing accurate soil moisture predictions.
  • the senor includes but is not limited to air temperature and humidity, carbon dioxide concentration, light, wind speed, atmospheric pressure, soil temperature, humidity, soil EC value, and other sensors related to agricultural production.
  • the sensor is connected to a control module and monitoring data is uploaded through the control module.
  • the intelligent farm task management system is identified to use smart algorithms for real-time production management decisions based on environmental production data, and can be deployed both locally on the farm and in the cloud.
  • the intelligent decision-making module can also check the system's status and provide statistical data analysis to the farm manager. It can also replace manual control commands with an intelligent decision-making module.
  • the intelligent decision-making module is based on real-time production environmental data, does not require human intervention, uses intelligent algorithms for production management decisions, and automatically sends decisions to control agricultural equipment for use in controlling agricultural equipment.
  • the intelligent farm task management system includes a wireless control module that is responsible for remote control of farm facilities and equipment.
  • Agricultural facilities include but are not limited to water and fertilizer integration, film rolling machines, fans, sunshades, wet curtains, heating, etc.
  • the executive control equipment includes but is not limited to, motors, electric valves, and electrical panels that can control agricultural facilities.
  • the executive control equipment is connected to the wireless control module and executes control commands issued by the relay, performing management operations such as turning on irrigation, turning on the roof membrane, turning on ventilation, turning on the external sunshade, and rotating the wet curtain for cooling.
  • the wireless control module includes a digital input and output interface that can receive sensor data and control equipment and facilities through a wireless gateway.
  • the wireless gateway has wireless network capabilities for communicating with sensors and facilities and uses a wired network to connect to the intelligent decision-making module.
  • 5G technology uploads information from various sensors on the one hand. It monitors the production environment data of the equipment, and on the other hand, issues control commands to the decisionmaking module.
  • a type of smart farm task management system includes a computer and a mobile application for management and employees, which are directly connected to the intelligent decision-making module and used for managing employee tasks. They can view the status of employees based on statistical analysis data, and can also use the module to issue commands and manage tasks automatically or manually, i

Abstract

An intelligent farm task management system comprising a data collection layer that is responsible for collecting data from various sources, a web service layer that provides the interface between the application layer and the cloud storage layer, a cloud storage layer that is responsible for storing the collected data and processed information, an application layer of the system which is responsible for processing and analyzing the data collected from the data collection layer and interacts with the cloud storage layer to store the processed data, and a user layer of the system is the front-end interface that allows users to interact with the system and provides users with real-time access to the data and analytics generated by the system.

Description

Description
Title of Invention: An intelligent farm task management system
Technical Field
[0001] The present invention relates to an agricultural field management system, to an agricultural field management method, and a management system in an agricultural field such as a farm, an agricultural field, and the like.
Background Art
[0002] Remote farm management has seen numerous advancements in recent years, particularly with the rapid adoption of farm management software and loT technologies. Some of which include:
[0003] 1 . Precision Agriculture: Remote farm management systems now use precision agriculture technology, which allows farmers to apply fertilizers and other farm inputs accurately, reducing waste and increasing yield.
[0004] 2. Drones and Satellites: Drones equipped with cameras and sensors provide real-time footage of crop growth and yield estimates, which can be helpful for farmers in optimizing their operations. Additionally, satellites are also used to observe crop growth and healthy soil from space, giving farmers access to comprehensive data.
[0005] 3. Real-time monitoring: Remote farm management systems now allow farmers to monitor their farm operations in real-time from any location. This significantly reduces the need to be physically present in the fields at all times.
[0006] 4. Automated irrigation systems: Advanced remote farm management systems make it easy to maintain and control automated irrigation systems. This has led to the optimization of water usage and reduction of water wastage, resulting in significant cost savings for farmers.
[0007] 5. Al and Machine Learning: Farms are leveraging Al and machine learning technologies to get improved insights into crop disease recognition, prediction of crop yields, and to make recommendations on how to optimize production.
[0008] Chinese Patent Publication No. CN112036717 discloses a smart agriculture product traceability management system based on the Internet of Things, which falls under the agricultural Internet of Things technology domain. The system encompasses various subsystems such as digital farm management, traceability code generation and printing, Internet of Things, agricultural remote sensing application, 5G-powered VR video monitoring, 5G-based hyperspectral video monitoring, cold chain standardization information, and e-commerce inventory and delivery integration.
[0009] Korean Patent Publication No. KR1020100011363 discloses a system and method for customized feeding in a farm using a remote management unit have been developed to provide the appropriate mixing ratio of feed for different livestock. The system comprises a farm data-acquiring unit that collects environmental and growth-related information along with weight and feed data. Farm data is transmitted and received via a farm data transceiver. The remote management unit receives the data via a network and manages the farm environment to ensure optimal growth conditions. The unit analyzes the amount of feed consumed by the livestock in response to changes in the environment and weight gain and provides customized feeding based on the raw materials and nutrient content of the feed, tailored to the growth stage of the livestock.
Summary of Invention
[0010] The proposed model is an intelligent farm task management system that utilizes information and communication technologies to collect and analyze realtime data for each farm. The system consists of five layers, including the data collection layer, web service layer, cloud storage layer, application layer, and user layer.
Technical Problem
[0011] Traditional farm management has always been a challenge due to various uncertainties, ranging from minor and usual changes to severe and unpredictable weather changes. For example, climate change can reduce 40% of maize crop diversity. Another problem is the shortage of labor in the agriculture industry. Recently, due to the work preferences of the new generation and the aging of the previous generation, the labor shortage has become a significant social problem. The labor shortage is particularly severe in rural areas compared to urban areas. On the other hand, under the pressure of increasing food safety requirements, increasing labor costs, and environmental degradation, the main task of farm management has turned from simple follow-up to more complex follow-up tasks.
[0012] Transitioning from traditional farming to "smart" farming using smart farm management systems can save time, costs, and resources and reduce energy consumption.
Advantageous Effects of Invention
[0013] Smart farm management systems can collect environmental data from large- scale farms in a wide range and upload them in real-time, and issue task management commands in real-time. Also, by using intelligent decision-making algorithms without human intervention, fully automated and flexible management of agricultural production can significantly reduce labor, improve management efficiency and technical level, prevent human intrusion as much as possible, improve the quality and productivity of agricultural products, and achieve the best results based on variable farm conditions. Moreover, the dynamic task generator helps workers minimize their idle time in case of any changes in the system. This improves their morale and reduces stress, errors, and enhances their confidence.
[0014] Furthermore, experts can use data collected from smart farming systems to make informed decisions about crop management. By analyzing data on weather patterns, soil conditions, and crop growth, they can determine the optimal time to plant, irrigate, and harvest crops. They can also use data to identify potential issues, such as disease or pest infestations, and take preventative measures to avoid crop loss. This proactive approach can save farmers time and money, and ultimately increase crop yields.
Brief Description of Drawings
[0015] Fig.1 illustrates a block diagram of the invention showing the overall configuration of a smart farm task management system.
[0016] Fig.2A and B show the operation of the software and how to determine the map of agricultural land and labor force and new machines and other activities.
[0017] Fig.3 shows the connection between input information and the types of information (records) output in the smart. [0018] Fig.4 shows the block diagram of the user environment and the system environment and the incorporation of the ANFIS, ASCE, and FAO methods for more accurate predictions.
[0019] Fig.5 shows an example of tasks performed records and assigned to farmers or employees created by the intelligent system.
Description of Embodiments
[0020] The system has a five-layer distributed architecture divided into a data collection layer, a web service layer, a cloud storage layer, an application layer, and a user layer.
[0021] 1 . Data Collection Layer: This layer is responsible for collecting data from various sources such as sensors, loT devices, and databases. The collected data can include information about temperature, humidity, soil moisture, crop growth, and weather conditions. The data is transmitted to the cloud storage layer for further processing and analysis. The database includes the data inputted by the farm manager. Ideally, the collected information includes data such as land use, farm map, employees, machinery, and other equipment. This module also allows users to add and receive information from other users and provides permissions, daily task management forms, and daily reports to the user. The farm production activity information (such as planting, pruning, irrigation, pesticide application, harvesting, and cleaning), labor information, and production process information are manually entered by the manager, while environmental information is automatically uploaded through web services.
[0022] 2. Web Service Layer: This layer provides the interface between the application layer and the cloud storage layer. It consists of web services that allow the application layer to retrieve and manipulate data stored in the cloud storage layer. The web services also enable communication between the different components of the system.
[0023] 3. Cloud Storage Layer: This layer is responsible for storing the collected data and processed information. It provides a scalable and secure platform for data storage and management. The cloud storage layer can also be used to perform data analysis and generate insights that can be used by the application layer to make decisions and take actions. The cloud storage layer includes multidimensional data resources (e.g., technical regulations data, primary data, and production archive data).
[0024] 4. The application layer of the system is responsible for processing and analyzing the data collected from the data collection layer. It performs various tasks such as data filtering, sorting, and aggregation to derive meaningful insights from the data. The layer also includes various algorithms and models that are used for predictive analytics and decision-making. The application layer interacts with the cloud storage layer to store the processed data and with the user layer to present insights and analytics in a user-friendly manner. The application layer consists of main functional modules that together support the efficient management of the farm, including the following modules:
[0025] • A communication module for transmitting and receiving data to and from the cloud system.
[0026] • A real-time monitoring module for the central server, which receives environmental information such as temperature or humidity from the system and analyzes information from each farm, performing real-time monitoring based on the results of the analysis.
[0027] • An information analysis module: the module analyzes environmental and farm data and provides the results of the analysis at specified intervals. This module also publishes reports on performance, workforce, and resources (weekly, monthly, and yearly).
[0028] • A wireless control module for facilities and machinery: which is responsible for remote control of farm facilities and equipment.
[0029] • A dynamic task generator module using real-time monitoring module data automatically determines and changes tasks using conditional logic in response to whether a criterion is above a threshold. For example, if the soil moisture system exceeds the threshold limit, it can send an automatic notification to the farmer to water the plants.
[0030] 5. The user layer of the system is the front-end interface that allows users to interact with the system. It includes various components such as a web or mobile application, dashboards, and reports. The user layer provides users with realtime access to the data and analytics generated by the system. It allows users to visualize the data, generate reports, and make informed decisions based on the insights provided by the system. The user layer also includes various features such as alerts, notifications, and collaboration tools to facilitate communication and collaboration among users.
[0031 ] Special details for implementing the invention of an integrated farm task management system using information and communication technology are as follows:
[0032] 1 . A block diagram shows the overall configuration of a smart farm task management system according to the preferred embodiment of the present invention. Referring to Figure 1 , smart farm task management, according to this embodiment, includes the following stages:
[0033] • Data collection: This system collects data from various sources such as sensors, weather forecasting applications, and pest detection systems.
[0034] • Data analysis: The collected data is analyzed to determine the current conditions of the farm such as moisture levels, pest presence, and weather conditions.
[0035] • Task generation: Based on the analyzed data, the system generates a list of tasks that need to be performed on the farm.
[0036] • Automatic decision making: The system uses conditional logic to dynamically change tasks based on farm conditions. For example, if it rains, irrigation tasks may be delayed and disease control tasks may take priority.
[0037] • Task execution: Generated tasks are assigned to the relevant personnel and executed, and the system updates the status.
[0038] • Feedback and monitoring: The system continuously monitors farm conditions and provides feedback to personnel regarding task execution.
[0039] • Record keeping: The system records all tasks performed, farm conditions, and personnel activities for future reference and analysis.
[0040] As shown in the Fig.2 a general flow of a farm task management system with conditional logic is illustrated, and it can be customized based on specific needs. [0041] As shown in Fig.2A,B the flow chart shows how to determine the map of agricultural land and labor force and new machines and other activities. Activities are in series, meaning that one activity takes precedence over another. For example, in a land, the first activity is plowing, then irrigation. Therefore, when these activities are given to employees as a task, the same rules apply: that is, someone who has an irrigation task cannot start working until someone who has a plowing task finished his work.
[0042] Automatic activities are determined according to the cultivation of the desired plant (or raising desired livestock). Example:
Figure imgf000009_0001
[0043] The time required to perform all the usual agricultural activities such as irrigation, spraying, etc. is determined according to the manager’s input. In the following, these activities are given to employees as a task. Example:
Figure imgf000009_0002
[0044] The proposed innovation is a state-of-the-art neural network system that aims to revolutionize agriculture management by predicting soil moisture content with high accuracy. This advanced system uses a combination of artificial neural networks, fuzzy logic, and optimization algorithms to gather, preprocess, and analyze data from various sources such as weather stations, soil sensors, and agricultural land location.
[0045] By accurately predicting soil moisture content, the system provides farmers with valuable insights into their operations, enabling them to make informed decisions about irrigation and other agricultural practices. This can lead to optimized operations, increased crop yields, and reduced water waste. Moreover, the system can adapt to changing conditions in real time, ensuring accurate predictions even in dynamic environments.
[0046] In one embodiment of the invention, the system employs a powerful neural network architecture, consisting of input, hidden, and output layers, to accurately model the complex relationships between the input variables and the output variables ( for example soil moisture). The BFGS optimization algorithm is used to iteratively update the weights of the neural network, resulting in a more accurate prediction model.
[0047] In addition to the BFGS optimization technique, the system also incorporates the ANFIS, ASCE, and FAO methods for more accurate predictions. The ANFIS method provides linguistic interpretability, while the ASCE method considers various factors such as precipitation, temperature, humidity, and wind speed. The FAO method takes into account factors such as climate, soil type, and crop characteristics, resulting in a more comprehensive and accurate prediction model as shown in Fig. 4.
[0048] In one embodiment of the invention, the system also employs data preprocessing and feature selection techniques to ensure that only the most relevant data is used for prediction. The data is aggregated from various sources such as sensor data, farm location, worker abilities, UAV camera images, and other unpredictable items.
[0049] Overall, the proposed innovation provides an advanced and comprehensive solution for predicting soil moisture content in agricultural settings, leveraging advanced technologies and methodologies to help farmers make informed decisions and achieve better outcomes. The flowchart shows one of the tasks of the farm, irrigation, where the system can optimize water and soil usage by providing accurate soil moisture predictions.
[0050] In one embodiment of the smart farm task management system disclosed in this invention, the sensor includes but is not limited to air temperature and humidity, carbon dioxide concentration, light, wind speed, atmospheric pressure, soil temperature, humidity, soil EC value, and other sensors related to agricultural production. The sensor is connected to a control module and monitoring data is uploaded through the control module. Here are some common situations on a farm and the tasks associated with each situation:
[0051] Weather:
[0052] A. Rainy weather: Tasks during and after rainfall include:
[0053] • Disease Control,
[0054] • Monitoring and reporting (frequency, intervals),
[0055] • Pesticide spraying,
[0056] • Removing any infected plants and weeds,
[0057] • Predicting floods,
[0058] • Transferring products and equipment to higher grounds,
[0059] • Installing flood protection barriers,
[0060] • Monitoring water levels,
[0061] • Protecting harvest,
[0062] • Covering harvested products, and
[0063] • Transferring harvested products from temporary storage to a dry location.
[0064] B. Dry weather: Tasks in case of drought include:
[0065] • Installing new irrigation systems,
[0066] • Increasing monitoring of irrigation systems,
[0067] • Monitoring soil moisture levels,
[0068] • Irrigating products to a certain amount, [0069] • Protecting products,
[0070] • Monitoring products for signs of damage,
[0071] • Using pesticides to a certain amount,
[0072] • Installing shading systems, and
[0073] • Monitoring nutrient levels in soil
[0074] Moisture levels:
[0075] A. Low moisture levels:
[0076] • Increasing irrigation frequency,
[0077] • Monitoring products for signs of damage,
[0078] • Using pesticides to a certain amount,
[0079] • Installing shading systems, and
[0080] • Monitoring nutrient levels in soil.
[0081] B. High moisture levels:
[0082] • Installing drainage systems,
[0083] • Monitoring water levels,
[0084] • Adjusting existing drainage systems,
[0085] • Monitoring and reporting (frequency, intervals),
[0086] • Pesticide spraying,
[0087] • Removing any infected plants and weeds.
[0088] Pest infestation:
[0089] A. Pest outbreak:
[0090] • Monitoring and reporting (frequency, intervals),
[0091] * Pesticide spraying,
[0092] • Removing any infected plants and weeds,
[0093] • Installing trapping systems, and
[0094] • Monitoring and controlling pests using biological methods [0095] B. Low pest infestation:
[0096] • Monitoring and reporting (frequency, intervals),
[0097] • Pesticide spraying to a certain amount,
[0098] • Installing trapping systems,
[0099] • Monitoring and controlling pests using biological methods.
[0100] The intelligent farm task management system is identified to use smart algorithms for real-time production management decisions based on environmental production data, and can be deployed both locally on the farm and in the cloud. The intelligent decision-making module can also check the system's status and provide statistical data analysis to the farm manager. It can also replace manual control commands with an intelligent decision-making module. The intelligent decision-making module is based on real-time production environmental data, does not require human intervention, uses intelligent algorithms for production management decisions, and automatically sends decisions to control agricultural equipment for use in controlling agricultural equipment.
[0101 ] The intelligent farm task management system includes a wireless control module that is responsible for remote control of farm facilities and equipment. Agricultural facilities include but are not limited to water and fertilizer integration, film rolling machines, fans, sunshades, wet curtains, heating, etc. The executive control equipment includes but is not limited to, motors, electric valves, and electrical panels that can control agricultural facilities. The executive control equipment is connected to the wireless control module and executes control commands issued by the relay, performing management operations such as turning on irrigation, turning on the roof membrane, turning on ventilation, turning on the external sunshade, and rotating the wet curtain for cooling.
[0102] The wireless control module includes a digital input and output interface that can receive sensor data and control equipment and facilities through a wireless gateway. The wireless gateway has wireless network capabilities for communicating with sensors and facilities and uses a wired network to connect to the intelligent decision-making module. 5G technology uploads information from various sensors on the one hand. It monitors the production environment data of the equipment, and on the other hand, issues control commands to the decisionmaking module.
[0103] In the present document a type of smart farm task management system is disclosed that includes a computer and a mobile application for management and employees, which are directly connected to the intelligent decision-making module and used for managing employee tasks. They can view the status of employees based on statistical analysis data, and can also use the module to issue commands and manage tasks automatically or manually, i

Claims

Claims
[Claim 1 ] n intelligent farm task management system comprising: a data collection layer which is responsible for collecting data from various sources such as sensors, loT devices, and databases and allows users to add and receive information from other users and provides permissions, daily task management forms, and daily reports to the user, a web service layer that provides the interface between the application layer and the cloud storage layer and consists of web services that allow the application layer to retrieve and manipulate data stored in the cloud storage layer and enable communication between the different components of the system, a cloud storage layer which is responsible for storing the collected data and processed information and performing data analysis and generates insights that can be used by the application layer to make decisions and take actions, the said data is transmitted from the data collection layer to the cloud storage layer for further processing and analysis, an application layer of the system which is responsible for processing and analyzing the data collected from the data collection layer and interacts with the cloud storage layer to store the processed data and with the user layer to present insights and analytics in a user-friendly manner, and a user layer of the system is the front-end interface that allows users to interact with the system and provides users with real-time access to the data and analytics generated by the system.
[Claim 2] The farm task management system of claim 1 , wherein the application layer consists of main functional modules that together support the efficient management of the farm, including the following modules:
• a communication module for transmitting and receiving data to and from the cloud system,
• a real-time monitoring module for the central server, which receives environmental information such as temperature or humidity from the system and analyzes information from each farm, performing real-time monitoring based on the results of the analysis,
• an information analysis module: the module analyzes environmental and farm data and provides the results of the analysis at specified intervals. This module also publishes reports on performance, workforce, and resources (weekly, monthly, and yearly),
• a wireless control module for facilities and machinery: which is responsible for remote control of farm facilities and equipment, and
• a dynamic task generator module using real-time monitoring module data automatically determines and changes tasks using conditional logic in response to whether a criterion is above a threshold, and includes various components such as a web or mobile application, dashboards, and reports.
[Claim 3] The farm task management system of claim 1 , wherein the collected data can include information about temperature, humidity, soil moisture, crop growth, and weather conditions.
[Claim 4] The farm task management system of claim 1 , wherein the database includes the data inputted by the farm manager in which data comprises land use, farm map, employees, machinery, and other equipment.
[Claim 5] The farm task management system of claim 1 , wherein the farm production activity information includes planting, pruning, irrigation, pesticide application, harvesting labor information, and production process information is manually entered by the manager.
[Claim 6] The farm task management system of claim 1 , wherein environmental information is automatically uploaded through web services.
[Claim 7] The farm task management system of claim 1 , wherein the cloud storage layer includes multidimensional data resources comprising technical regulations data, primary data, and production archive data.
[Claim 8] The farm task management system of claim 1 , wherein includes a computer and a mobile application for management and employees, which are used for managing employee tasks and the status of employees based on statistical analysis data is checked and can also issue commands and manage tasks.
[Claim 9] The farm task management system of claim 1 , further comprising a powerful neural network architecture, consisting of input, hidden, and output layers, to accurately model the complex relationships between the input variables and the output variables.
[Claim 10] The farm task management system of claim 1 , wherein the system also employs data preprocessing and feature selection techniques to ensure that only the most relevant data is used for prediction.
[Claim 11] The farm task management system of claim 1 , wherein the data is aggregated from various sources such as sensor data, farm location, worker abilities, UAV camera images, and other unpredictable items.
PCT/IB2023/054365 2023-04-27 2023-04-27 An intelligent farm task management system WO2024013577A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/IB2023/054365 WO2024013577A1 (en) 2023-04-27 2023-04-27 An intelligent farm task management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/IB2023/054365 WO2024013577A1 (en) 2023-04-27 2023-04-27 An intelligent farm task management system

Publications (1)

Publication Number Publication Date
WO2024013577A1 true WO2024013577A1 (en) 2024-01-18

Family

ID=89536103

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2023/054365 WO2024013577A1 (en) 2023-04-27 2023-04-27 An intelligent farm task management system

Country Status (1)

Country Link
WO (1) WO2024013577A1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210117887A1 (en) * 2019-10-22 2021-04-22 Tycom, Inc. Methods and systems for farming task management
US11263707B2 (en) * 2017-08-08 2022-03-01 Indigo Ag, Inc. Machine learning in agricultural planting, growing, and harvesting contexts

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11263707B2 (en) * 2017-08-08 2022-03-01 Indigo Ag, Inc. Machine learning in agricultural planting, growing, and harvesting contexts
US20210117887A1 (en) * 2019-10-22 2021-04-22 Tycom, Inc. Methods and systems for farming task management

Similar Documents

Publication Publication Date Title
US10349584B2 (en) System and method for plant monitoring
Sinwar et al. AI-based yield prediction and smart irrigation
CN111504371A (en) Big data service system
CN113228041B (en) Detection of infection of plant diseases using improved machine learning
Saha et al. IoT‐enabled agricultural system application, challenges and security issues
Murugamani et al. Machine learning technique for precision agriculture applications in 5G-based internet of things
KR20220071405A (en) Agricultural support system and method using big data of smart farm
CN113273449A (en) Digital twin body construction method for precise monitoring of sunlight greenhouse
CN112465109A (en) Green house controlling means based on cloud limit is in coordination
Anand et al. Applications of Internet of Things (IoT) in agriculture: The need and implementation
Costa et al. Greenhouses within the Agricultura 4.0 interface
Singh et al. Role of IoT technology in agriculture for reshaping the future of farming in India: a review
Pal et al. AI, IoT and Robotics in Smart Farming: Current Applications and Future Potentials
KR20230004218A (en) Facility cultivation complex environmental control system
Ingole et al. Design Approaches for Internet of Things Based System Model for Agricultural Applications
WO2024013577A1 (en) An intelligent farm task management system
Singh Sustainable and Smart Agriculture: A Holistic Approach
Ahmad et al. Smart Intelligent Precision Agriculture
Sethuraman et al. Smart Agriculture Applications Using Internet of Things
Balakrishna et al. The automatic agricultural crop maintenance system using runway scheduling algorithm: fuzzyc-LR for IoT networks
Mustafa et al. Intelligent Irrigation System-Automation Using IoT Technology: A Review
Navaneethan et al. Advanced Technologies for Precision Agriculture and Farming
Thilagu et al. Artificial Intelligence and Internet of Things Enabled Smart Farming for Sustainable Development: The Future of Agriculture
Marline Joys Kumari et al. Smart Irrigation and Cultivation Recommendation System for Precision Agriculture Driven by IoT
Kotov et al. Digital technologies in AIC management

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23839117

Country of ref document: EP

Kind code of ref document: A1